import os import gradio as gr import time import requests list_stack=[] api_url="https://90f6-34-16-143-189.ngrok-free.app/upload" def get_transcription_whissper_api(audio,api_url=api_url): audio_file = open(audio, 'rb') files = {'audio': ('audio.wav', audio_file)} response = requests.post(api_url, files=files) json_response = response.json() if response.status_code == 200: print("Audio file uploaded successfully.") return(json_response['message']) else: return("Error uploading the audio file.") def empty_list(): list_stack.clear() def inference_upload(audio,state=""): state+= get_transcription_whissper_api(audio)+" " return (state,state) def inference(audio,state=""): state += get_transcription_whissper_api(audio) + " " delimiter=" " list_stack.append(state) all_transcriptions=(delimiter.join(list_stack)) return (state,all_transcriptions) css = """ .gradio-container { font-family: 'IBM Plex Sans', sans-serif; } .gr-button { color: white; border-color: black; background: black; } input[type='range'] { accent-color: black; } .dark input[type='range'] { accent-color: #dfdfdf; } .container { max-width: 1030px; margin: auto; padding-top: 1.5rem; } .details:hover { text-decoration: underline; } .gr-button { white-space: nowrap; } .gr-button:focus { border-color: rgb(147 197 253 / var(--tw-border-opacity)); outline: none; box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000); --tw-border-opacity: 1; --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color); --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color); --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity)); --tw-ring-opacity: .5; } .footer { margin-bottom: 45px; margin-top: 35px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } .prompt h4{ margin: 1.25em 0 .25em 0; font-weight: bold; font-size: 115%; } .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; margin-top: 1.5rem !important; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; } #share-btn { all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important; } #share-btn * { all: unset; } """ block = gr.Blocks(css=css) with block: gr.HTML( """
This page can be used to simply try out the capabilities of tagaloc + english transcription. The model used is the smallest because this process only runs with small computations. Speed and accuracy can be improved with more powerful computing.